def _run_one_size(self, algo, n_samples, n_features, param_overrides={}, dataset_param_overrides={}):
data = gen_data(self.dataset_name, n_samples, n_features, **dataset_param_overrides)
# sklearn
algo.reload()
skl_timer = BenchmarkTimer(self.n_reps)
for rep in skl_timer.benchmark_runs():
algo.run(data, **param_overrides)
skl_elapsed = np.min(skl_timer.timings)
# patched sklearn
d4p.patch_sklearn()
algo.reload()
d4p_timer = BenchmarkTimer(self.n_reps)
for rep in d4p_timer.benchmark_runs():
algo.run(data, **param_overrides)
d4p_elapsed = np.min(d4p_timer.timings)
d4p.unpatch_sklearn()
speedup = skl_elapsed / d4p_elapsed
print(f"{algo.name} (n_samples={n_samples}, n_features={n_features})"
f" [skl={skl_elapsed}, d4p={d4p_elapsed} speedup={speedup}]")
return dict(
skl_time=skl_elapsed,
d4p_time=d4p_elapsed,
speedup=speedup,
n_samples=n_samples,
n_features=n_features,
**param_overrides,
**dataset_param_overrides
)
def parse_args(parser,
size=None,
loop_types=(),
n_jobs_supported=True,
prefix='sklearn'):
'''
Add common arguments useful for most benchmarks and parse.
Parameters
----------
parser : argparse.ArgumentParser
Parser to which the arguments should be added.
size : tuple of int, optional
Enable '--size' argument with this default size.
If None (default), no '--size' argument will be added.
loop_types : iterable of str, optional
Add arguments like '--fit-inner-loops' and '--fit-outer-loops',
useful for tweaking runtime of the benchmark.
n_jobs_supported : bool
If set to True, generate a n_jobs member in the argparse Namespace
corresponding to the optimal n_jobs parameter for scikit-learn.
Otherwise, n_jobs will be set to None.
prefix : str, optional, default 'sklearn'
The default prefix to report
Returns
-------
parser : argparse.ArgumentParser
Parser to which the arguments were added.
This is the same parser that was passed to this function.
'''
parser.add_argument('-n',
'--num-threads',
'--core-number',
default=-1,
dest='threads',
type=int,
help='Number of threads to use')
parser.add_argument('-a',
'--arch',
default='?',
help='Machine architecture, for bookkeeping')
parser.add_argument('-b',
'--batch',
'--batchID',
default='?',
help='Batch ID, for bookkeeping')
parser.add_argument('-p',
'--prefix',
default=prefix,
help='Prefix string, for bookkeeping')
parser.add_argument('-v',
'--verbose',
default=False,
action='store_true',
help='Output extra debug messages')
parser.add_argument('--data-format',
type=str,
default='numpy',
choices=('numpy', 'pandas', 'cudf'),
help='Data format: numpy (default), pandas, cudf')
parser.add_argument('--data-order',
type=str,
default='C',
choices=('C', 'F'),
help='Data order: C (row-major, default) or'
'F (column-major)')
parser.add_argument('-d',
'--dtype',
type=np.dtype,
default=np.float64,
choices=(np.float32, np.float64),
help='Data type: float64 (default) or float32')
parser.add_argument('--check-finiteness',
default=False,
action='store_true',
help='Check finiteness in sklearn input check'
'(disabled by default)')
parser.add_argument('--output-format',
type=str,
default='json',
choices=('json'),
help='Output format: json')
parser.add_argument('--time-method',
type=str,
default='box_filter',
choices=('box_filter'),
help='Method used for time mesurements')
parser.add_argument('--box-filter-measurements',
type=int,
default=100,
help='Maximum number of measurements in box filter')
parser.add_argument('--inner-loops',
default=100,
type=int,
help='Maximum inner loop iterations '
'(we take the mean over inner iterations)')
parser.add_argument('--outer-loops',
default=100,
type=int,
help='Maximum outer loop iterations '
'(we take the min over outer iterations)')
parser.add_argument('--time-limit',
default=10.,
type=float,
help='Target time to spend to benchmark')
parser.add_argument('--goal-outer-loops',
default=10,
type=int,
dest='goal',
help='Number of outer loops to aim '
'while automatically picking number of '
'inner loops. If zero, do not automatically '
'decide number of inner loops.')
parser.add_argument('--seed',
type=int,
default=12345,
help='Seed to pass as random_state')
parser.add_argument('--dataset-name',
type=str,
default=None,
help='Dataset name')
parser.add_argument('--no-intel-optimized',
default=False,
action='store_true',
help='Use no intel optimized version. '
'Now avalible for scikit-learn benchmarks'),
parser.add_argument('--device',
default='None',
type=str,
choices=('host', 'cpu', 'gpu', 'None'),
help='Execution context device')
for data in ['X', 'y']:
for stage in ['train', 'test']:
parser.add_argument(f'--file-{data}-{stage}',
type=argparse.FileType('r'),
help=f'Input file with {data}_{stage},'
'in NPY format')
if size is not None:
parser.add_argument('-s',
'--size',
default=size,
type=_parse_size,
dest='shape',
help='Problem size, delimited by "x" or ","')
params = parser.parse_args()
if not params.no_intel_optimized:
try:
from daal4py.sklearn import patch_sklearn
patch_sklearn()
except ImportError:
print(
'Failed to import daal4py.sklearn.patch_sklearn.'
'Use stock version scikit-learn',
file=sys.stderr)
params.device = 'None'
else:
if params.device != 'None':
print(
'Device context is not supported for stock scikit-learn.'
'Please use --no-intel-optimized=False with'
f'--device={params.device} parameter. Fallback to --device=None.',
file=sys.stderr)
params.device = 'None'
# disable finiteness check (default)
if not params.check_finiteness:
sklearn_disable_finiteness_check()
# Ask DAAL what it thinks about this number of threads
num_threads = prepare_daal_threads(num_threads=params.threads)
if params.verbose:
print(f'@ DAAL gave us {num_threads} threads')
n_jobs = None
if n_jobs_supported:
n_jobs = num_threads = params.threads
# Set threading and DAAL related params here
setattr(params, 'threads', num_threads)
setattr(params, 'n_jobs', n_jobs)
# Set size string parameter for easy printing
if size is not None:
setattr(params, 'size', size_str(params.shape))
# Very verbose output
if params.verbose:
print(f'@ params = {params.__dict__}')
return params
import numpy as np
from daal4py.sklearn import patch_sklearn
patch_sklearn()
from sklearn.linear_model import LinearRegression
from timeit import default_timer as timer
from sklearn.metrics import mean_squared_error
import pandas as pd
import common
NUM_LOOPS = 100
print("Computing for Linear Regression with Daal Patch")
def run_inference(num_observations: int = 1000):
"""Run xgboost for specified number of observations"""
# Load data
train_x_df = common.get_test_data_df(X=common.X_df, size=num_observations)
train_y = common.get_test_data_y(size=num_observations)
num_rows = len(train_x_df)
######################
print("_______________________________________")
print("Total Number of Rows", num_rows)
run_times = []
inference_times = []
for _ in range(NUM_LOOPS):
start_time = timer()
reg = LinearRegression().fit(train_x_df, train_y)
#predictor.compute(data, MODEL)
end_time = timer()
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software distributed under
# the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
# ANY KIND, either express or implied. See the License for the specific language
# governing permissions and limitations under the License.
import os
import time
import modin.pandas as pd
from modin.experimental.engines.omnisci_on_ray.frame.omnisci_worker import OmnisciServer
from sklearn import config_context
import daal4py.sklearn as sklearn
sklearn.patch_sklearn()
from sklearn.model_selection import train_test_split
import sklearn.linear_model as lm
import numpy as np
def read():
columns_names = [
"YEAR0",
"DATANUM",
"SERIAL",
"CBSERIAL",
"HHWT",
"CPI99",
"GQ",
"QGQ",